#--------- Install packages to for today's session ----------#
# install.packages("tidyverse", dependencies = TRUE) # This package should already be installed on Jupyter Hub

#--------- Load packages to for today's session ----------#
library(tidyverse)
library(viridis)

-- Attaching core tidyverse packages ---------------------------------------------------------------- tidyverse 2.0.0 --
v dplyr     1.1.0     v readr     2.1.4
v forcats   1.0.0     v stringr   1.5.0
v ggplot2   3.4.3     v tibble    3.2.1
v lubridate 1.9.2     v tidyr     1.3.0
v purrr     1.0.2     
-- Conflicts ---------------------------------------------------------------------------------- tidyverse_conflicts() --
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()
i Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
Loading required package: viridisLite

# set working directory
getwd()
list.files("./data")

# read our file in with read_csv()
embryos.df <- read_csv("data/embryo_data_long_merged.csv", col_types = "cdffffdfllddfddffff")

# explore our loaded data frame
head(embryos.df)

# Increment a by 2, the bad way...
a <- 2
a <- a+2
a <- a+2
a <- a+2
a <- a+2
a <- a+2
a <- a+2
a <- a+2
a <- a+2
a <- a+2
a

# Increment 'anything' using a for loop
anything = 10

# Set up your for loop with a 'tally' count
for (tally in 1:1000) {
    anything <- anything + 2
    }

tally
anything

# Use the seq() function
seq(from = 1, to = 10, by = 0.5)

# let's use seq() in a for loop to count, no braces but indentation
for(variable in seq(1, 10, 0.5)) 
    print(variable)
    print("middle but not really")
print("This is the end")

[1] 1
[1] 1.5
[1] 2
[1] 2.5
[1] 3
[1] 3.5
[1] 4
[1] 4.5
[1] 5
[1] 5.5
[1] 6
[1] 6.5
[1] 7
[1] 7.5
[1] 8
[1] 8.5
[1] 9
[1] 9.5
[1] 10
[1] "middle but not really"
[1] "This is the end"

# for loop on a single line
for(variable in seq(1, 10, 0.5)) print(variable); print("middle but not really"); print("This is the end")

[1] 1
[1] 1.5
[1] 2
[1] 2.5
[1] 3
[1] 3.5
[1] 4
[1] 4.5
[1] 5
[1] 5.5
[1] 6
[1] 6.5
[1] 7
[1] 7.5
[1] 8
[1] 8.5
[1] 9
[1] 9.5
[1] 10
[1] "middle but not really"
[1] "This is the end"

# for loop on a single line, with brackets
for(variable in seq(1, 10, 0.5)) {print(variable); print("middle but not really")}; print("This is the end")

[1] 1
[1] "middle but not really"
[1] 1.5
[1] "middle but not really"
[1] 2
[1] "middle but not really"
[1] 2.5
[1] "middle but not really"
[1] 3
[1] "middle but not really"
[1] 3.5
[1] "middle but not really"
[1] 4
[1] "middle but not really"
[1] 4.5
[1] "middle but not really"
[1] 5
[1] "middle but not really"
[1] 5.5
[1] "middle but not really"
[1] 6
[1] "middle but not really"
[1] 6.5
[1] "middle but not really"
[1] 7
[1] "middle but not really"
[1] 7.5
[1] "middle but not really"
[1] 8
[1] "middle but not really"
[1] 8.5
[1] "middle but not really"
[1] 9
[1] "middle but not really"
[1] 9.5
[1] "middle but not really"
[1] 10
[1] "middle but not really"
[1] "This is the end"

# Use the rep() function to print the number 1-5, 8 times
rep(x = 1:5, times = 8)

# for loop version variables need to be set
rm(result, i)  # Remove the variables result and i, if they exist.
x <- 1:5
n <- 8
result <- x # What happens if we remove this line?

# Build our for loop
for (i in 1:(n-1)){
    result <- c(result, x)
    print(result)
  }

result
i

Warning message in rm(result, i):
"object 'result' not found"
Warning message in rm(result, i):
"object 'i' not found"

 [1] 1 2 3 4 5 1 2 3 4 5
 [1] 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5
 [1] 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5
 [1] 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5
 [1] 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5
 [1] 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5
 [1] 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5 1 2 3
[39] 4 5

# Clear some memory and check th value of variables that may already exist
rm(result, j)
cat("The prior value of i is :", i, "\n")

# for loop version variables need to be set
x <- 1:5 
n <- 8
result <- 100

# Build a local for loop - this completely isolates any new variables from the global scope
local(
    for (i in 1:n){
        result <- c(result, x)
        print(result)
        j <- result # assign a value to j
    }
)

cat("The value of result is: ", result, "\n")
cat("The value of i is :", i, "\n")
cat("The value of j is :", j)

Warning message in rm(result, j):
"object 'j' not found"

The prior value of i is : 7 
[1] 100   1   2   3   4   5
 [1] 100   1   2   3   4   5   1   2   3   4   5
 [1] 100   1   2   3   4   5   1   2   3   4   5   1   2   3   4   5
 [1] 100   1   2   3   4   5   1   2   3   4   5   1   2   3   4   5   1   2   3
[20]   4   5
 [1] 100   1   2   3   4   5   1   2   3   4   5   1   2   3   4   5   1   2   3
[20]   4   5   1   2   3   4   5
 [1] 100   1   2   3   4   5   1   2   3   4   5   1   2   3   4   5   1   2   3
[20]   4   5   1   2   3   4   5   1   2   3   4   5
 [1] 100   1   2   3   4   5   1   2   3   4   5   1   2   3   4   5   1   2   3
[20]   4   5   1   2   3   4   5   1   2   3   4   5   1   2   3   4   5
 [1] 100   1   2   3   4   5   1   2   3   4   5   1   2   3   4   5   1   2   3
[20]   4   5   1   2   3   4   5   1   2   3   4   5   1   2   3   4   5   1   2
[39]   3   4   5
The value of result is:  100 
The value of i is : 7

Error in cat("The value of j is :", j): object 'j' not found
Traceback:

1. cat("The value of j is :", j)

# Pull down the structure and colnames of our embryos.df
str(embryos.df, give.attr = FALSE)
colnames(embryos.df)

spc_tbl_ [9,802 x 19] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
 $ experiment   : chr [1:9802] "200707_N2_LUAm1_0M_72hpi" "200707_N2_LUAm1_10M_72hpi" "200707_JU1400_LUAm1_0M_72hpi" "200707_JU1400_LUAm1_10M_72hpi" ...
 $ wormNumber   : num [1:9802] 1 1 1 1 1 1 1 1 1 1 ...
 $ infectionDate: Factor w/ 9 levels "200704","200711",..: 1 1 1 1 1 1 1 1 1 1 ...
 $ wormStrain   : Factor w/ 18 levels "N2","JU1400",..: 1 1 2 2 3 3 4 4 5 5 ...
 $ sporeStrain  : Factor w/ 6 levels "LUAm1","MAM1",..: 1 1 1 1 1 1 1 1 1 1 ...
 $ sporeDose    : Factor w/ 11 levels "0","10","4","3.5",..: 1 2 1 2 1 2 1 2 1 2 ...
 $ sporesM_cm2  : num [1:9802] 0 0.354 0 0.354 0 ...
 $ doseLevel    : Factor w/ 6 levels "Mock","Medium",..: 1 2 1 2 1 2 1 2 1 2 ...
 $ spores       : logi [1:9802] FALSE FALSE FALSE FALSE FALSE FALSE ...
 $ meronts      : logi [1:9802] FALSE TRUE FALSE TRUE FALSE TRUE ...
 $ embryos      : num [1:9802] 18 7 10 0 12 0 5 9 11 0 ...
 $ expTimepoint : num [1:9802] 72 72 72 72 72 72 72 72 72 72 ...
 $ infectionType: Factor w/ 1 level "continuous": 1 1 1 1 1 1 1 1 1 1 ...
 $ totalWorms   : num [1:9802] 1000 1000 1000 1000 1000 1000 1000 1000 1000 1000 ...
 $ plateSize    : num [1:9802] 6 6 6 6 6 6 6 6 6 6 ...
 $ fixingDate   : Factor w/ 9 levels "200707","200714",..: 1 1 1 1 1 1 1 1 1 1 ...
 $ stainingDate : Factor w/ 10 levels "200803","200810",..: 1 1 1 1 1 1 1 1 1 1 ...
 $ slideDate    : Factor w/ 9 levels "200804","200811",..: 1 1 1 1 1 1 1 1 1 1 ...
 $ imagingDate  : Factor w/ 13 levels "200806","200813",..: 1 1 1 1 1 1 1 1 1 1 ...

# Grab a list of infection dates from the dataset
days = unique(embryos.df$infectionDate)

for (i in 1:length(days)) {
    
    plot <-
        embryos.df %>% 
        filter(infectionDate %in% days[1:i]) %>% 
    
        ggplot(.) +
        # 2. Aesthetics
        aes(x = infectionDate, y = embryos, colour = infectionDate) +
    
        labs(title = paste0("Embryos per infection date with ", i, " days")) + # Add a title based on the day range
        guides(colour = "none") +
    
        # 4. Geoms
        geom_jitter()
    
    suppressWarnings(print(plot)) # Drop the warnings when we print the plot
    
    Sys.sleep(2) # Pause the system for 2 seconds
    
}

# for loop in a single line, with brackets
for(variable in c("I", "You", "We all")) { 
    print(variable) 
    print("scream;") 
} 
print ("for ice cream")

[1] "I"
[1] "scream;"
[1] "You"
[1] "scream;"
[1] "We all"
[1] "scream;"
[1] "for ice cream"

# Build a very specific subset of data looking at only N2 and JU1400 populations 
# infected by a medium does of LUAm1
subdata <-
    embryos.df %>% 
    filter(wormStrain %in% c("N2", "JU1400"),
           sporeStrain == "LUAm1",
           doseLevel == "Medium"
          )
    
    # create an empty data frame to store the output of the for loop
    result <- data.frame(infectionDate = unique(subdata$infectionDate),
                         difference = NA,
                         p_value = NA)
    
result

# for loop to calculate difference in means between N2 and JU1400 infected by LUAm1 on the same date

for(i in result$infectionDate) {
    # Generate a t-test on subset by day
    t <- t.test(embryos ~ wormStrain, subdata[subdata$infectionDate == i, ])
    # write the results to our data frame
    result[result$infectionDate == i, "difference"] <- diff(t$estimate)
    result[result$infectionDate == i, "p_value"] <- t$p.value
}

result

subdata_ttest <-
    # Pass the subdata
    subdata %>% 
    # Group the data
    group_by(infectionDate) %>% 
    # Use Summarise to do the repetitive work for you
    summarise(difference = diff(t.test(embryos ~ wormStrain)$estimate),
              p_values = t.test(embryos ~ wormStrain)$p.value)

subdata_ttest

# Practice with an if() statement
x <- c("what", "is", "truth")

if("truth" %in% x) {
  print("Truth is found")
}

[1] "Truth is found"

# Practice with a complex if() statement
x <- c("what", "is", "truth")

# Build a complex cascade of statements looking for Truth
if("TRUTH" %in% x) {
    print("TRUTH is found")
} else if ("Truth" %in% x) { 
    print ("Truth is found")
} else { # notice the placement of else is directly after the closing }
    print ("The truth is out there somewhere")
}

[1] "The truth is out there somewhere"

# Pick a student grade
grade <- 69
letterGrade <- "Unassigned"

# Long if statement for choosing grades
if (grade >= 90) { letterGrade <- "A+"
} else if (grade >= 85) { letterGrade <- "A"
} else if (grade >= 80) { letterGrade <- "A-"
} else if (grade >= 77) { letterGrade <- "B+"
} else if (grade >= 73) { letterGrade <- "B"
} else if (grade >= 70) { letterGrade <- "B-"
} else {letterGrade <- "FZ"} 
    
# What is the assigned letter grade?  
letterGrade

# Only proceed if you have data in embryos.df
numVector <- c(1,2,3,4)

if(length(numVector) >0) {
    # You have data to look at so print it
    print(numVector)
    
    if(sum(numVector) > 8) {
        # Your vector has a minimum sum
        print(sum(numVector))
        
        if(prod(numVector) < 20) {
            # Your vector has a product of less than 20
            print(prod(numVector))
        } else { 
            print("product is >= 20")
        }
    } else {
        print("sum is <= 8 ")
    }
} else {
    print("vector is empty")
}

[1] 1 2 3 4
[1] 10
[1] "product is >= 20"

# Check if our file exists
# Use dir() to return a vector of file names and then ask if any match ours. 
if(sum(dir() == "embryo_subdata_ttest.csv") > 0) {
    
  print("Stop! A file with that same name already exists")

} else {
    
    # The file does not exist, print the go-ahead and save the file
    print("No files with the same name. Good to go!")
    
}

write_csv(x = subdata_ttest, file = "embryo_subdata_ttest.csv", col_names = TRUE)

[1] "Stop! A file with that same name already exists"

# Check if our file exists
# Use dir() to return a vector of file names and then ask if any match ours. 
if("embryo_subdata_ttest.csv" %in% dir()) {
    
  print("Stop! A file with that same name already exists")

} else {
    
    # The file does not exist, print the go-ahead and save the file
    print("No files with the same name. Good to go!")
    # Write the file as part of the same control statement
    write_csv(x = subdata_ttest, file = "embryo_subdata_ttest.csv", col_names = TRUE)   
}

[1] "Stop! A file with that same name already exists"

# Use if when x is TRUE
x <- TRUE
if(x) "True result"

# Use if when x is FALSE
x <- FALSE
if(x) "False result"

# Use if when x is NA
x <- NA
if(x) "NA result"

Error in if (x) "NA result": missing value where TRUE/FALSE needed
Traceback:

# You can make complex logical expressions as long as they evaluate to either TRUE or FALSE!
x <- TRUE
y <- FALSE
z <- if(x | y) "At least one variable was TRUE!!!"

z

# Use if else when x is TRUE
x <- TRUE
if(x) "True result" else "False result"

# Use if else when x is FALSE
x <- FALSE
if(x) "True result" else "False result"

# A simple example of ifelse()
rm(a)

i <- 8

ifelse(test = i < 5, yes = a <- 0, no = a <- 1)

# a

# A complex vectorized example of ifelse()
i <- c(1:10)

ifelse(test = i < 5, yes = 0, no = 1) # Can we achieve this in a simpler way?

# Don't forget that we can quickly convert booleans to numeric!
as.numeric(i >= 5)

# Pick your favourite pokemon!
pokemon <- "squirtle"
dexType <- "unknown"

# Look at how long this listing gets
if (pokemon == "bulbasaur") {dexType <- "plant"
} else if (pokemon == "squirtle") {dexType <- "water"
} else if (pokemon == "charmander") {dexType <- "fire"
} else if (pokemon == "pikachu") {dexType <- "electric"
} else if (pokemon == "lapras") {dexType <- "water/ice"
} else if (pokemon == "snorlax") {dexType <- "normal"
} else if (pokemon == "magikarp") {dexType <- "water" 
} else {dexType <- "unknown input"}
                                   
dexType

# Pick your favourite pokemon!
pokemon <- "lapras"

dexType <-
switch(pokemon,
       "bulbasaur" = "plant",
       "squirtle" = "water",
       "charmander" = "fire",
       "pikachu" = "electric",
       "lapras" = "water/ice",
       "snorlax" = "normal",
       "magikarp" = "water",
       "unknown input")

dexType

# Initialize our variable for conditional assessment
x <- 0

# Generate the while loop, incrementing x by 1 on each iteration, as long as x < 10
while(x < 10) {
  x <- x + 1
  print(x)
  }

[1] 1
[1] 2
[1] 3
[1] 4
[1] 5
[1] 6
[1] 7
[1] 8
[1] 9
[1] 10

# Loop will be ignored if the condition is FALSE and nothing gets printed
x <- 20

while(x < 10) {
    x <- x + 1
    print(x)
}

# Set your initial value
programmer <- " at the grocery store"

# Build your while loop
while(programmer == " at the grocery store") {
  print("buy some eggs")
  programmer <- "bought some eggs"   # What would happen if we commented out this line?
}

print(programmer)
# When do we provide the opportunity to change?

[1] "buy some eggs"
[1] "bought some eggs"

# using next within our for loop
for(i in 1:10) {
  
    if (i >= 5 & i <= 8) {
        next # skips ends the current iteration of the loop
    }
    print(i)
}

i

[1] 1
[1] 2
[1] 3
[1] 4
[1] 9
[1] 10

# Using break
for(i in 1:10) {
  
    if (i == 5) {
        break # completely exits the loop
    }
    print(i)
}
i

[1] 1
[1] 2
[1] 3
[1] 4

# Using repeat() to endlessly loop

i = 1

repeat {

    if (i == 20) {
        break # completely exits the loop
    }
    print(i)
    i = i + 1
}
i

[1] 1
[1] 2
[1] 3
[1] 4
[1] 5
[1] 6
[1] 7
[1] 8
[1] 9
[1] 10
[1] 11
[1] 12
[1] 13
[1] 14
[1] 15
[1] 16
[1] 17
[1] 18
[1] 19

# Using repeat() to demonstrate that conditional placement matters.
i = 1

# What numbers will this code print?
# What happens if we move the print command around?
repeat {

    i = i + 1
    if (i == 20) {
        break # completely exits the loop
    }
    print(i)
}

[1] 2
[1] 3
[1] 4
[1] 5
[1] 6
[1] 7
[1] 8
[1] 9
[1] 10
[1] 11
[1] 12
[1] 13
[1] 14
[1] 15
[1] 16
[1] 17
[1] 18
[1] 19

library(repr)

# Note that the standard display size is a 7x7 inch space. let's double the width
options(repr.plot.width=21, repr.plot.height=7)

ggplot(embryos.df[embryos.df$infectionDate == "190423",]) +
    #2 Aesthetics
    aes(x = wormStrain, y = embryos, fill = wormStrain) +
    # 4. Geoms
    geom_boxplot()

# Loop through the possible infection dates
for (i in unique(embryos.df$infectionDate)) {

    infectionRep <-
    
        ggplot(embryos.df[embryos.df$infectionDate == i,]) +
            #2 Aesthetics
            aes(x = wormStrain, y = embryos, fill = wormStrain) +
            theme_grey() +
            ggtitle("Embryo counts") + # plot title
            # 4. Geoms
            geom_boxplot()
    
    print(infectionRep) # This is the only way to view the plot in a for loop
        
    # Save each plot as it's generated
    ggsave(plot = infectionRep, filename = paste(i, "boxplot.png", sep = "_"), path = "data/" , 
           scale=2, device = "png", units = c("cm"))
}

Saving 33.9 x 33.9 cm image
Saving 33.9 x 33.9 cm image

Saving 33.9 x 33.9 cm image

Saving 33.9 x 33.9 cm image

Saving 33.9 x 33.9 cm image

Saving 33.9 x 33.9 cm image

Saving 33.9 x 33.9 cm image

Saving 33.9 x 33.9 cm image

Saving 33.9 x 33.9 cm image

# Loop through the possible infection dates
for (i in unique(embryos.df$infectionDate)) {

    infectionRep <-
    
        ggplot(embryos.df[embryos.df$infectionDate == i,]) +
            # 2. Aesthetics
            aes(x = wormStrain, y = embryos, fill = wormStrain) +
            theme_grey() +
            ggtitle(paste0("Embryo counts on infection date: ", i)) + # plot title
            # 4. Geoms
            geom_boxplot() +
            # 6. Facets
            facet_grid(sporeStrain ~ doseLevel)  ### 2.1.0 Facet our data by strain and dose
    
        # Only print the brackish dataset
    if (i == "190423") {
        print(infectionRep) # The only way to see the plot is to print it within a for loop
    }
            
    # Save each plot as it's generated
    ggsave(plot = infectionRep, filename = paste(i, "boxplot.facet.png", sep = "_"), path = "data/" , 
           scale=2, device = "png", width = 20, height = 10, units = c("cm"))
}

# Description: This function, given a set of data from the embryo.df format will produce
#              a faceted series of box plots for a specific infections date splitting by sporeStrain and doseLevel

# Input: 
# data.df: a data frame at least with the following column names
# $infectionDate, $wormStrain, $sporeStrain, $doseLevel
# infDate: a character string used to subset the data

# Output: make.facet.plot will generate a facet plot from data.df based on the infDate variable
# The plot will be saved to a file ending in "boxplot.facet.function.png"

make.facet.plot = function(data.df, infDate) {

    infectionRep <-

        # You could also filter your data with filter() and piping instead!
        ggplot(data.df[data.df$infectionDate == infDate,]) +
    
            # 2. Aesthetics
            aes(x = wormStrain, y = embryos, fill = wormStrain) +
            theme_grey() +
            ggtitle(paste0("Embryo counts on infection date: ", infDate)) + # plot title
    
            # 4. Geoms
            geom_boxplot() +

            # 6. Facets
            facet_grid(sporeStrain ~ doseLevel)
    
    # Print the plot 
    print(infectionRep)
    
    # Save each plot as it's generated
    ggsave(plot = infectionRep, filename = paste(infDate, "boxplot.facet.makeFunction.png", sep = "_"), path = "data/" , 
           scale=2, device = "png", width = 20, height = 10, units = c("cm"))

} # End of make.face.plot

unique(embryos.df$infectionDate)

# Use a for loop to iterate through the first 3 levels of infectionDate
for (i in unique(embryos.df$infectionDate)[1:3]){

    # Call on our function now
    make.facet.plot(data.df = embryos.df, i)
}

# Description: This function, given a set of data from the embryo.df format will produce
#              a faceted series of box plots for a specific infections date splitting by sporeStrain and doseLevel

# Input: 
# data.df: a data frame at least with the following column names
# $infectionDate, $wormStrain, $sporeStrain, $doseLevel
# infDate: a character string used to subset the data

# Output: make.facet.plot will generate a facet plot from data.df based on the infDate variable
# The plot will be saved to a file ending in "boxplot.facet.function.png"
# It will return 
# [1] subset data
# [2] ggplot object 
# [3] save plot filename

save.facet.plot = function(data.df, infDate) {

    ### 3.2.0 We've updated the plot to use a filter() function!
    infection.data <- data.df %>% filter(infectionDate == infDate)
    
    infectionPlot <-

    ggplot(infection.data) +

        # 2. Aesthetics
        aes(x = wormStrain, y = embryos, fill = wormStrain) +
        theme_grey() +
        ggtitle(paste0("Embryo counts on infection date: ", infDate)) + # plot title

        # 4. Geoms
        geom_boxplot() +

        # 6. Facets
        facet_grid(sporeStrain ~ doseLevel)

    # Save the name of the plot file
    save.file <- paste(infDate, "boxplot.facet.saveFunction.png", sep = "_")
       
    # Save each plot as it's generated
    ggsave(plot = infectionPlot, filename = paste(infDate, "boxplot.facet.saveFunction.png", sep = "_"), path = "data/" , 
           scale=2, device = "png", width = 20, height = 10, units = c("cm"))
    
    ### 3.2.0 return the file name and data subset
    # Create a list so that you can send multiple objects back as a single object
    return(list(infection.data, infectionPlot, save.file))    
    
}

# Call on save.facet.plot function now

inf200704.plot <- save.facet.plot(embryos.df, "200704")

# Look at the data
head(inf200704.plot[[1]])

# Display the plot to output
inf200704.plot[[2]]

# What's the file name?
inf200704.plot[[3]]

# Rerun our function without an infection date
save.facet.plot(embryos.df)

Error in `filter()`:
i In argument: `infectionDate == infDate`.
Caused by error:
! argument "infDate" is missing, with no default
Traceback:

1. save.facet.plot(embryos.df)
2. data.df %>% filter(infectionDate == infDate)   # at line 19 of file <text>
3. filter(., infectionDate == infDate)
4. filter.data.frame(., infectionDate == infDate)
5. filter_rows(.data, dots, by)
6. filter_eval(dots, mask = mask, error_call = error_call)
7. withCallingHandlers(mask$eval_all_filter(dots, env_filter), error = dplyr_error_handler(dots = dots, 
 .     mask = mask, bullets = filter_bullets, error_call = error_call), 
 .     warning = function(cnd) {
 .         local_error_context(dots, i, mask)
 .         warning_handler(cnd)
 .     }, `dplyr:::signal_filter_one_column_matrix` = function(e) {
 .         warn_filter_one_column_matrix(call = error_call)
 .     }, `dplyr:::signal_filter_across` = function(e) {
 .         warn_filter_across(call = error_call)
 .     }, `dplyr:::signal_filter_data_frame` = function(e) {
 .         warn_filter_data_frame(call = error_call)
 .     })
8. mask$eval_all_filter(dots, env_filter)
9. eval()
10. .handleSimpleError(function (cnd) 
  . {
  .     local_error_context(dots, i = frame[[i_sym]], mask = mask)
  .     if (inherits(cnd, "dplyr:::internal_error")) {
  .         parent <- error_cnd(message = bullets(cnd))
  .     }
  .     else {
  .         parent <- cnd
  .     }
  .     message <- c(cnd_bullet_header(action), i = if (has_active_group_context(mask)) cnd_bullet_cur_group_label())
  .     abort(message, class = error_class, parent = parent, call = error_call)
  . }, "argument \"infDate\" is missing, with no default", base::quote(eval()))
11. h(simpleError(msg, call))
12. abort(message, class = error_class, parent = parent, call = error_call)
13. signal_abort(cnd, .file)

# Description: This function, given a set of data from the embryo.df format will produce
#              a faceted series of box plots for a specific infections date splitting by sporeStrain and doseLevel

# Input: 
# data.df: a data frame at least with the following column names
# $infectionDate, $wormStrain, $sporeStrain, $doseLevel
# infDate: a character string used to subset the data

# Output: make.facet.plot will generate a facet plot from data.df based on the infDate variable
# The plot will be saved to a file ending in "boxplot.facet.function.png"
# It will return 
# [1] subset data
# [2] ggplot object 
# [3] save plot filename

### 3.3.0 Set the default value of infDate to 190423
save.facet.plot = function(data.df, infDate = "190423") {

    # We've updated the plot to use a filter() function!
    infection.data <- data.df %>% filter(infectionDate == infDate)
    
    infectionPlot <-

    ggplot(infection.data) +

        # 2. Aesthetics
        aes(x = wormStrain, y = embryos, fill = wormStrain) +
        theme_grey() +
        ggtitle(paste0("Embryo counts on infection date: ", infDate)) + # plot title

        # 4. Geoms
        geom_boxplot() +

        # 6. Facets
        facet_grid(sporeStrain ~ doseLevel)

    # Save the name of the plot file
    save.file = paste(infDate, "graph.facet.function.png", sep = "_")

    # Save each plot as it's generated
    ggsave(plot = infectionPlot, filename = paste(infDate, "boxplot.facet.saveFunction.png", sep = "_"), path = "data/" , 
           scale=2, device = "png", width = 20, height = 10, units = c("cm"))
    
    #return the file name and data subset
    # Create a list so that you can send multiple objects back as a single object
    return(list(infection.data, infectionPlot, save.file))    
    
}

# Rerun our function without an infection date
save.facet.plot(embryos.df)

[[1]]
# A tibble: 3,643 x 19
   experiment          wormNumber infectionDate wormStrain sporeStrain sporeDose
   <chr>                    <dbl> <fct>         <fct>      <fct>       <fct>    
 1 190426_VC20019_LUA~          1 190423        VC20019    LUAm1       0        
 2 190426_VC20019_LUA~          1 190423        VC20019    LUAm1       10       
 3 190426_VC20019_LUA~          1 190423        VC20019    LUAm1       20       
 4 190426_N2_LUAm1_0M~          1 190423        N2         LUAm1       0        
 5 190426_N2_LUAm1_10~          1 190423        N2         LUAm1       10       
 6 190426_N2_LUAm1_20~          1 190423        N2         LUAm1       20       
 7 190426_AB1_LUAm1_0~          1 190423        AB1        LUAm1       0        
 8 190426_AB1_LUAm1_1~          1 190423        AB1        LUAm1       10       
 9 190426_AB1_LUAm1_2~          1 190423        AB1        LUAm1       20       
10 190426_JU397_LUAm1~          1 190423        JU397      LUAm1       0        
# i 3,633 more rows
# i 13 more variables: sporesM_cm2 <dbl>, doseLevel <fct>, spores <lgl>,
#   meronts <lgl>, embryos <dbl>, expTimepoint <dbl>, infectionType <fct>,
#   totalWorms <dbl>, plateSize <dbl>, fixingDate <fct>, stainingDate <fct>,
#   slideDate <fct>, imagingDate <fct>

[[2]]

[[3]]
[1] "190423_graph.facet.function.png"

# Define our function(s)
make.power = function(power) { # This sets the variable values (via lexical scoping) of the exponent
    
    pow = function(base) { # When we call on the resulting function it will require a base value
        
        base^power # Make the actual calculation
    }    
}

# Define a new function that does cubic calculations
cube = make.power(3)

# Now we have a function cube() that takes a parameter called base to calculate base^power

# Call on our cubic function using a base of 4
cube(4)

# Description: This function, given a set of data from the embryo.df format will produce
#              a faceted series of box plots for a specific infections date splitting by sporeStrain and doseLevel

# Input: 
# data.df: a data frame at least with the following column names
# $infectionDate, $wormStrain, $sporeStrain, $doseLevel
# infDate: a character string used to subset the data

# Output: make.facet.plot will generate a facet plot from data.df based on the infDate variable
# The plot will be saved to a file ending in "boxplot.facet.function.png"
# It will return 
# [1] subset data
# [2] ggplot object 
# [3] save plot filename

### 3.4.0 Define a new function where we set the data.df parameter as input.
set.facet.plot = function(data.df) {

    # Set the default value of infDate to 190423
    save.facet.plot = function(infDate = "190423") {

        # We've updated the plot to use a filter() function!
        infection.data <- data.df %>% filter(infectionDate == infDate)

        infectionPlot <-

        ggplot(infection.data) +

            # 2. Aesthetics
            aes(x = wormStrain, y = embryos, fill = wormStrain) +
            theme_grey() +
            ggtitle(paste0("Embryo counts on infection date: ", infDate)) + # plot title

            # 4. Geoms
            geom_boxplot() +

            # 6. Facets
            facet_grid(sporeStrain ~ doseLevel)

        # Save the name of the plot file
        save.file = paste(infDate, "graph.facet.function.png", sep = "_")

        # Save each plot as it's generated
        ggsave(plot = infectionPlot, filename = paste(infDate, "boxplot.facet.saveFunction.png", sep = "_"), path = "data/" , 
               scale=2, device = "png", width = 20, height = 10, units = c("cm"))

        #return the file name and data subset
        return(list(infection.data, infectionPlot, save.file))    

    }
}

# Step 2. Make a function where the data set is embryos.df
make.embryo.plot <- set.facet.plot(embryos.df)

# Make a plot and filter it by infection Date
infection.results <- make.embryo.plot("200704")

infection.results[[2]]

# Let's see what happens when we work with the log function
log10(1)
log10(0)
log10(-1)

Warning message in eval(expr, envir, enclos):
"NaNs produced"

get.log10 = function(x) {
    
    if(x <= 0) stop("Execution stopped: ", x, " is not acceptable input")
    log10(x)
}

get.log10(1) # test our function
get.log10(-1) # Check it will stop when it's supposed to
get.log10(10) # Will this code run?

Error in get.log10(-1): Execution stopped: -1 is not acceptable input
Traceback:

1. get.log10(-1)
2. stop("Execution stopped: ", x, " is not acceptable input")   # at line 3 of file <text>

# Simplify our main function which takes in pre-filtered data and plots it
# Define a new function where we set the data.df parameter as input.
# @Input
# infection.data: a filtered set of infection data that represents a single replicate date
# infDate: the actual replicate date that will be used in the title information

# Set the default value of infDate to 190423
make.facet.plot = function(infection.data, infDate) {

    infectionPlot <-

    ggplot(infection.data) +

        # 2. Aesthetics
        aes(x = wormStrain, y = embryos, fill = wormStrain) +
        theme_grey() +
        ggtitle(paste0("Embryo counts on infection date: ", infDate)) + # plot title

        # 4. Geoms
        geom_boxplot() +

        # 6. Facets
        facet_grid(sporeStrain ~ doseLevel)

    return(infectionPlot)

}

# Make a function to filter data, make the plot, then save the plot
# @Input
# data.df: A dataset containing individual observations of embryo counts with at least: 
#          $wormStrain, $embryos, $infectionDate
# infDate: The infection date to filter data.df
#
# @Output
# List of 3 objects: 1) Filtered infection data
#                    2) A ggplot object of the infection data
#                    3) file name of saved plot

save.facet.plot = function(data.df, infDate) {

    # filter the data
    infection.data <- filter(data.df, infectionDate == infDate)
        
    # make the plotted data
    infection.plot <- make.facet.plot(infection.data, infDate)

    # generate a save file name
    save.file = paste(infDate, "graph.facet.saveFunction2.png", sep = "_")

    # save the plot
    ggsave(plot = infection.plot, filename = save.file, path = "data/" ,
         scale=2, device = "png", units = c("cm"))

    #return the file name and data subset
    return(list(infection.data, infection.plot, save.file))   
}

# save a facet plot but look at the output of the plot
save.facet.plot(embryos.df, "200704")[[2]]

Saving 33.9 x 33.9 cm image

# save a facet plot but but don't provide a salinity type
save.facet.plot(embryos.df)[[2]]

Error in `filter()`:
i In argument: `infectionDate == infDate`.
Caused by error:
! argument "infDate" is missing, with no default
Traceback:

1. save.facet.plot(embryos.df)
2. filter(data.df, infectionDate == infDate)   # at line 15 of file <text>
3. filter.data.frame(data.df, infectionDate == infDate)
4. filter_rows(.data, dots, by)
5. filter_eval(dots, mask = mask, error_call = error_call)
6. withCallingHandlers(mask$eval_all_filter(dots, env_filter), error = dplyr_error_handler(dots = dots, 
 .     mask = mask, bullets = filter_bullets, error_call = error_call), 
 .     warning = function(cnd) {
 .         local_error_context(dots, i, mask)
 .         warning_handler(cnd)
 .     }, `dplyr:::signal_filter_one_column_matrix` = function(e) {
 .         warn_filter_one_column_matrix(call = error_call)
 .     }, `dplyr:::signal_filter_across` = function(e) {
 .         warn_filter_across(call = error_call)
 .     }, `dplyr:::signal_filter_data_frame` = function(e) {
 .         warn_filter_data_frame(call = error_call)
 .     })
7. mask$eval_all_filter(dots, env_filter)
8. eval()
9. .handleSimpleError(function (cnd) 
 . {
 .     local_error_context(dots, i = frame[[i_sym]], mask = mask)
 .     if (inherits(cnd, "dplyr:::internal_error")) {
 .         parent <- error_cnd(message = bullets(cnd))
 .     }
 .     else {
 .         parent <- cnd
 .     }
 .     message <- c(cnd_bullet_header(action), i = if (has_active_group_context(mask)) cnd_bullet_cur_group_label())
 .     abort(message, class = error_class, parent = parent, call = error_call)
 . }, "argument \"infDate\" is missing, with no default", base::quote(eval()))
10. h(simpleError(msg, call))
11. abort(message, class = error_class, parent = parent, call = error_call)
12. signal_abort(cnd, .file)

# Make a function to filter data, make the plot, then save the plot
save.facet.plot = function(data.df, infDate) {
    
    # Initiate a tryCatch and assign its output to a variable
    out <- tryCatch({
        # filter the data
        infection.data <- filter(data.df, infectionDate == infDate)
        # What happens if we pick a non-existent infection date or if the parameter is not set?
    },
    error = function(c) { # The actual error information is passed in as the variable "c"
        # Assume the error occurs when no infDate is provided
        message("Error: potentially missing parameter information")
        
        return(NULL)
        # return NULL so we can recognize an error has occurred
        # You're kind of a function inside a function.
        # when you return, you'll leave to the next section.
        
    }) # End tryCatch
    
    if (!is.null(out)) {
        
        # make the plotted data
        infection.plot <- make.facet.plot(infection.data, infDate)

        # generate a save file name
        save.file = paste(infDate, "graph.facet.saveFunction.tryCatch.png", sep = "_")

        # save the plot
        ggsave(plot = infection.plot, filename = save.file, path = "data/" ,
             scale=2, device = "png", units = c("cm"))

        #return the file name and data subset
        return(list(infection.data, infection.plot, save.file))          
    }
 
    else return(out) # if it's an error we'll get the NULL
}

# save a facet plot but look at the output of the plot
save.facet.plot(embryos.df)[[2]]

Error: potentially missing parameter information

NULL

# Make a function to filter data, make the plot, then save the plot
save.facet.plot = function(data.df, infDate) {

    # Initiate a tryCatch and assign its output to a variable
    out <- tryCatch({
        # filter the data
        infection.data <- filter(data.df, infectionDate == infDate)
        # What happens if we pick a non-existent infection date or if the parameter is not set?
    },
    error = function(c) { # The actual error information is passed in as the variable "c"
        # Assume the error occurs when no infDate is provided
        message("Warning: No infection date provided")
        message("substituting with a first-level value")
        
        ### 3.6.5 Remember: we are in a mini function at the moment
        # We need to go up a level and set infDate within the save.facet.plot function
        # Set it to the first level of $infectionDate
        infDate <<- levels(data.df$infectionDate)[1] 
        
        # Then we'll remake the data subset
        infection.data <<- filter(data.df, infectionDate == infDate)
        # This will allow us to proceed with the rest of the code as though nothing were amiss

        # return(NULL)
        # return NULL so we can recognize an error has occurred
        # You're kind of a function inside a function.
        # when you return, you'll leave to the next section.
        
    }) # End tryCatch  
    
    # make the plotted data
    infection.plot <- make.facet.plot(infection.data, infDate)

    # generate a save file name
    save.file = paste(infDate, "graph.facet.saveFunction.tryCatchv2.png", sep = "_")

    # save the plot
    ggsave(plot = infection.plot, filename = save.file, path = "data/" ,
         scale=2, device = "png", units = c("cm"))

    #return the file name and data subset
    return(list(infection.data, infection.plot, save.file))
}

# save a facet plot but look at the output of the plot
save.facet.plot(embryos.df)[[2]]

Warning: No infection date provided

substituting with a first-level value

Saving 33.9 x 33.9 cm image

# Make a function to filter data, make the plot, then save the plot
save.facet.plot = function(data.df, infDate) {
    
    # Initiate a tryCatch and assign its output to a variable
    out <- tryCatch({
        # filter the data
        infection.data <- filter(data.df, infectionDate == infDate)
        # What happens if we pick a non-existent infection date or if the parameter is not set?
    },
    error = function(c) { # The actual error information is passed in as the variable "c"
        # Assume the error occurs when no infDate is provided
        message("Warning: No infection date provided")
        message("substituting with a first-level value")
        
        # Remember: we are in a mini function at the moment
        # We need to go up a level and set infDate within the save.facet.plot function
        # Set it to the first level of $infectionDate
        infDate <<- levels(data.df$infectionDate)[1] 
        
        # Then we'll remake the data subset
        infection.data <- filter(data.df, infectionDate == infDate)
        # This will allow us to proceed with the rest of the code as though nothing were amiss

        # return(NULL)
        # return NULL so we can recognize an error has occurred
        # You're kind of a function inside a function.
        # when you return, you'll leave to the next section.
        
    },
    ### Set up a finally section which runs regardless of whether or not an error has been caught
    # You could put all or some of your end-code here depending on your needs
    # We'll move all the post-catch code into here for fun
    finally = {
        # make the plotted data
        infection.plot <- make.facet.plot(infection.data, infDate)

        # generate a save file name
        save.file = paste(infDate, "graph.facet.saveFunction.tryCatchv2.png", sep = "_")

        # save the plot
        ggsave(plot = infection.plot, filename = save.file, path = "data/" ,
             scale=2, device = "png", units = c("cm"))

        #return the file name and data subset
        return(list(infection.data, infection.plot, save.file))
        
    }) # End tryCatch  
}

# save a facet plot but look at the output of the plot
save.facet.plot(embryos.df)[[2]]

Warning: No infection date provided

substituting with a first-level value

Saving 33.9 x 33.9 cm image

save.facet.plot(embryos.df, "221019")[[2]]

Saving 33.9 x 33.9 cm image

Error in `combine_vars()`:
! Faceting variables must have at least one value
Traceback:

1. save.facet.plot(embryos.df, "221019")
2. tryCatch({
 .     infection.data <- filter(data.df, infectionDate == infDate)
 . }, error = function(c) {
 .     message("Warning: No infection date provided")
 .     message("substituting with a first-level value")
 .     infDate <<- levels(data.df$infectionDate)[1]
 .     infection.data <- filter(data.df, infectionDate == infDate)
 . }, finally = {
 .     infection.plot <- make.facet.plot(infection.data, infDate)
 .     save.file = paste(infDate, "graph.facet.saveFunction.tryCatchv2.png", 
 .         sep = "_")
 .     ggsave(plot = infection.plot, filename = save.file, path = "data/", 
 .         scale = 2, device = "png", units = c("cm"))
 .     return(list(infection.data, infection.plot, save.file))
 . })   # at line 5-47 of file <text>
3. ggsave(plot = infection.plot, filename = save.file, path = "data/", 
 .     scale = 2, device = "png", units = c("cm"))   # at line 41-42 of file <text>
4. grid.draw(plot)
5. grid.draw.ggplot(plot)
6. print(x)
7. print.ggplot(x)
8. ggplot_build(x)
9. ggplot_build.ggplot(x)
10. layout$setup(data, plot$data, plot$plot_env)
11. setup(..., self = self)
12. self$facet$compute_layout(data, self$facet_params)
13. compute_layout(..., self = self)
14. combine_vars(data, params$plot_env, rows, drop = params$drop)
15. cli::cli_abort("Faceting variables must have at least one value")
16. rlang::abort(message, ..., call = call, use_cli_format = TRUE, 
  .     .frame = .frame)
17. signal_abort(cnd, .file)

# Make a function to filter data, make the plot, then save the plot
save.facet.plot = function(data.df, infDate) {
    
    # Initiate a tryCatch and assign its output to a variable
    out <- tryCatch({
        # filter the data
        infection.data <- filter(data.df, infectionDate == infDate)
        # What happens if we pick a non-existent infection date or if the parameter is not set?
    },
    error = function(c) { # The actual error information is passed in as the variable "c"
        # Assume the error occurs when no infDate is provided
        message("Error: No infection date provided")
        message("substituting with a first-level value")
        
        # Remember: we are in a mini function at the moment
        # We need to go up a level and set infDate within the save.facet.plot function
        infDate <<- levels(data.df$infectionDate)[1] 
        
        # Then we'll remake the data subset
        infection.data <<- filter(data.df, infectionDate == infDate)
        # This will allow us to proceed with the rest of the code as though nothing were amiss
               
    }) # End the tryCatch having made a subset or default version if no infDate is supplied
    
    # In the case of an INCORRECT infDate there are a couple of ways to go about doing it
    # Check if our filtered data has any rows
    if(nrow(infection.data) > 0) {
        
        infection.plot <- make.facet.plot(infection.data, infDate)

        # generate a save file name
        save.file = paste(infDate, "graph.facet.saveFunction.tryCatchv2.png", sep = "_")

        # save the plot
        ggsave(plot = infection.plot, filename = save.file, path = "data/" ,
             scale=2, device = "png", units = c("cm"))

        #return the file name and data subset
        return(list(infection.data, infection.plot, save.file))
        
    } else {
    
        # filter results in 0-row subset
        return(rep("Warning: data filtering resulted in 0-row subset", 3))
    }    
}

# save.facet.plot(embryos.df)[[2]]
save.facet.plot(embryos.df, "221019")[[2]]

# Comprehension Question 3.0.0
# Make a function to filter data, make the plot, then save the plot
save.facet.plot.updated = function(data.df, infDate) {
    
    # Initiate a tryCatch and assign its output to a variable
    out <- tryCatch({
        # filter the data
        infection.data <- filter(data.df, infectionDate == infDate)
        # What happens if we pick a non-existent infection date or if the parameter is not set?
    },
    error = function(c) { # The actual error information is passed in as the variable "c"
        # Assume the error occurs when no infDate is provided
        message("Error: No infection date provided")
        message("substituting with a first-level value")
        
        # Remember: we are in a mini function at the moment
        # We need to go up a level and set infDate within the save.facet.plot function
        infDate <<- levels(data.df$infectionDate)[1] 
        
        # Then we'll remake the data subset
        infection.data <<- filter(data.df, infectionDate == infDate)
        # This will allow us to proceed with the rest of the code as though nothing were amiss
        
        return(NULL)
        # return NULL so we can recognize an error has occurred
        # You're kind of a function inside a function.
        # when you return, you'll leave to the next section.
        
    }) # End the tryCatch having made a subset or default version if no infDate is supplied
    
    # In the case of an INCORRECT infDate, how can we tell if it isn't a possible value?
    if(...) {
        
        infection.plot <- make.facet.plot(infection.data, infDate)

        # generate a save file name
        save.file = paste(infDate, "graph.facet.saveFunction.tryCatchv2.png", sep = "_")

        # save the plot
        ggsave(plot = infection.plot, filename = save.file, path = "data/" ,
             scale=2, device = "png", units = c("cm"))

        #return the file name and data subset
        return(list(infection.data, infection.plot, save.file))
        
    } else {
    
        # filter results in 0-row subset
        return(rep("Error: infData provided is not a level of infectionDate", 3))
    }    
}

#?source
# Load data and information from another R script
source("./data/Lecture07.R")

# See what variables and functions you have in memory
print(ls())

 [1] "a"                 "anything"          "codon_translation"
 [4] "codonToAA"         "cube"              "days"             
 [7] "dexType"           "embryos.df"        "get.log10"        
[10] "goodbye.class"     "grade"             "i"                
[13] "inf200704.plot"    "infection.data"    "infection.results"
[16] "infectionRep"      "letterGrade"       "make.embryo.plot" 
[19] "make.facet.plot"   "make.power"        "n"                
[22] "numVector"         "plot"              "pokemon"          
[25] "programmer"        "result"            "save.facet.plot"  
[28] "set.facet.plot"    "subdata"           "subdata_ttest"    
[31] "surprise.class"    "t"                 "tally"            
[34] "variable"          "x"                 "y"                
[37] "z"

# To see which functions are available in memory
lsf.str()

codonToAA : function (codon)  
cube : function (base)  
get.log10 : function (x)  
goodbye.class : function ()  
make.embryo.plot : function (infDate = "190423")  
make.facet.plot : function (infection.data, infDate)  
make.power : function (power)  
save.facet.plot : function (data.df, infDate)  
set.facet.plot : function (data.df)  
surprise.class : function (name)

# Let's look at a new function from "Lecture07.R"
codonToAA

function (codon) 
{
    return(str_replace_all(codon, codon_translation))
}

# Look up newly added variables
codon_translation

# Use codonToAA on a single codon
codonToAA("AUA")

# Use codonToAA on multiple codons
codonToAA(c("AUA", "UAG"))  %>% str_flatten()

# Let's try surprise.class()

surprise.class("class")

print(ls())

save(inf200704.plot, subdata, embryos.df, 
     file="./data/Lecture07.RData")   # Note the filetype we use to save data is "RData"

 [1] "a"                 "anything"          "codon_translation"
 [4] "codonToAA"         "cube"              "days"             
 [7] "dexType"           "embryos.df"        "get.log10"        
[10] "goodbye.class"     "grade"             "i"                
[13] "inf200704.plot"    "infection.data"    "infection.results"
[16] "infectionRep"      "letterGrade"       "make.embryo.plot" 
[19] "make.facet.plot"   "make.power"        "n"                
[22] "numVector"         "plot"              "pokemon"          
[25] "programmer"        "result"            "save.facet.plot"  
[28] "set.facet.plot"    "subdata"           "subdata_ttest"    
[31] "surprise.class"    "t"                 "tally"            
[34] "variable"          "x"                 "y"                
[37] "z"

# Save an image of everything to an RData file
save.image(file="./data/Lecture07.all.RData")

# Clear memory
rm(list = ls())
# check that it's clear
print(ls())

character(0)

# reload it all
load("./data/Lecture07.all.RData")

print(ls())

 [1] "a"                 "anything"          "codon_translation"
 [4] "codonToAA"         "cube"              "days"             
 [7] "dexType"           "embryos.df"        "get.log10"        
[10] "goodbye.class"     "grade"             "i"                
[13] "inf200704.plot"    "infection.data"    "infection.results"
[16] "infectionRep"      "letterGrade"       "make.embryo.plot" 
[19] "make.facet.plot"   "make.power"        "n"                
[22] "numVector"         "plot"              "pokemon"          
[25] "programmer"        "result"            "save.facet.plot"  
[28] "set.facet.plot"    "subdata"           "subdata_ttest"    
[31] "surprise.class"    "t"                 "tally"            
[34] "variable"          "x"                 "y"                
[37] "z"

# Time to run our final function together
...

infectionDate	difference	p_value
<fct>	<dbl>	<dbl>
200704	-9.940000	1.737888e-25
200711	-8.400000	6.851135e-20
200718	-11.560000	1.451323e-28
200818	-10.980000	4.447701e-25
200822	-14.120000	1.175066e-34
200901	-10.460000	8.480135e-28
190423	-9.028205	2.445116e-23

infectionDate	difference	p_values
<fct>	<dbl>	<dbl>
200704	-9.940000	1.737888e-25
200711	-8.400000	6.851135e-20
200718	-11.560000	1.451323e-28
200818	-10.980000	4.447701e-25
200822	-14.120000	1.175066e-34
200901	-10.460000	8.480135e-28
190423	-9.028205	2.445116e-23

experiment	wormNumber	infectionDate	wormStrain	sporeStrain	sporeDose	sporesM_cm2	doseLevel	spores	meronts	embryos	expTimepoint	infectionType	totalWorms	plateSize	fixingDate	stainingDate	slideDate	imagingDate
<chr>	<dbl>	<fct>	<fct>	<fct>	<fct>	<dbl>	<fct>	<lgl>	<lgl>	<dbl>	<dbl>	<fct>	<dbl>	<dbl>	<fct>	<fct>	<fct>	<fct>
200707_N2_LUAm1_0M_72hpi	1	200704	N2	LUAm1	0	0.000000	Mock	FALSE	FALSE	18	72	continuous	1000	6	200707	200803	200804	200806
200707_N2_LUAm1_10M_72hpi	1	200704	N2	LUAm1	10	0.353857	Medium	FALSE	TRUE	7	72	continuous	1000	6	200707	200803	200804	200806
200707_JU1400_LUAm1_0M_72hpi	1	200704	JU1400	LUAm1	0	0.000000	Mock	FALSE	FALSE	10	72	continuous	1000	6	200707	200803	200804	200806
200707_JU1400_LUAm1_10M_72hpi	1	200704	JU1400	LUAm1	10	0.353857	Medium	FALSE	TRUE	0	72	continuous	1000	6	200707	200803	200804	200806
200707_ED3052A_LUAm1_0M_72hpi	1	200704	ED3052A	LUAm1	0	0.000000	Mock	FALSE	FALSE	12	72	continuous	1000	6	200707	200803	200804	200806
200707_ED3052A_LUAm1_10M_72hpi	1	200704	ED3052A	LUAm1	10	0.353857	Medium	FALSE	TRUE	0	72	continuous	1000	6	200707	200803	200804	200806

Lecture 07: Flow control¶

Student Name: Live HTML Testing updater¶

Student ID:¶

0.1.0 About Introduction to R¶

0.1.1 Where is this course headed?¶

0.1.2 How do we get there? Step-by-step.¶

0.1.3 What kind of coding style will we learn?¶

0.2.0 Class Objectives¶

0.3.0 A legend for text format in Jupyter markdown¶

0.4.0 Lecture and data files used in this course¶

0.4.1 Weekly Lecture and skeleton files¶

0.4.2 Live-coding HTML page¶

0.4.3 Post-lecture PDFs and Recordings¶

0.4.4 Microsporidia infection data set description¶

0.4.4.1 Dataset 1: embryo_data_long_merged.csv¶

0.4.4.2 Source file: lecture07.R¶

0.5.0 Packages used in this lesson¶

1.0.0 Control flow moves you beyond linear programming¶

1.1.0 Use for() loops to repeat commands for a maximum number of iterations¶

1.1.1 The for loop can be described in three stages¶

1.1.2 Common functions are just pre-programmed for() loops¶

1.1.3 Self-referencing variables must be declared outside your loops¶

1.1.4 The scope (persistence) of variables is tied to when/where they are declared¶

1.1.4.1 The local() scope isolates your code from the global environment¶

1.1.5 Cycle through values using a for() loop¶

1.1.6 Iterating through a vector of elements in a for() loop¶

1.1.6.1 for loops run beneath the group_by()¶

1.2.0 Generate conditional branches using if() statements¶

1.2.1 More complex conditional branches may require the else() statement¶

1.2.2 if() statements can be nested¶

1.2.3 Use if() statements to generate system messages¶

1.2.3.1 Use effective control flow to ensure your intentions are met¶

1.2.4 The if() and else statement is an effective control flow statement for simple tasks¶

1.2.5 The ifelse() statement allows vectorized conditional assignment¶

1.2.6 Replace long/simple/cascading if statements with switch()¶

1.3.0 Running loops without a predetermined end-point¶

1.3.1 while() loops run conditionally¶

1.3.1.1 Conditional loops can become endless¶

1.3.2 Using next and break to exit any kind of looping structure¶

1.3.3 repeat loops run endlessly unless specifically interrupted by break¶

1.3.4 Be mindful of how you iterate through your loops¶

1.3.4.1 Use loops to simplify your code, but don't re-invent the wheel!¶

Comprehension Question 1.0.0 Answer:¶

2.0.0 Increasing our complexity by combining for() loops with ggplot()¶

2.1.0 Take advantage of for loop variables to customize output in each loop¶

3.0.0 Can we jump around our code to perform different tasks?¶

3.0.1 Do One Thing - but do it well¶

3.0.2 Document your functions¶

3.1.0 Declare your own functions with function()¶

3.1.1 Once your declared functions are stored in memory, they can be called from anywhere.¶

3.2.0 Retrieve data from your function using the return() command¶

3.3.0 Arguments for your functions can have a default value¶

3.4.0 User-defined functions can also define functions¶

3.5.0 The stop() function exits a function with a message¶

3.6.0 Use tryCatch() to identify errors without stopping¶

3.6.1 Remember that your functions should do one thing well¶

3.6.2 Call on subfunctions within your function to simplify debugging¶

3.6.3 Test the boundary cases of your function¶

3.6.4 Implement a tryCatch() series to try and capture your error¶

3.6.5 Use tryCatch() to set values within your function¶

3.6.6 Use flow control to handle error situations¶

4.0.0 Taking full advantage of your R environment¶

4.1.0 Keep all of your helper functions and subroutines in a file as a source()¶

4.2.0 Query your environment with ls() to find variables and functions¶

4.2.1 Check functions loaded into memory with lsf.str()¶

4.3.0 save() objects or your whole kernel memory!¶

4.3.1 save.image() saves your entire workspace¶

4.4.0 load() .RData files into memory¶

5.0.0 There is always more to explore!¶

5.1.0 Post-course survey¶

5.2.0 Submit your completed skeleton notebook (2% of final grade)¶

5.3.0 Final assignment guidelines (50% of final grade)¶

5.3.0 Acknowledgements¶

5.4.0 Your DataCamp academic subscription¶

5.5.0 Resources¶

1.1.0 Use `for()` loops to repeat commands for a maximum number of iterations¶

1.1.1 The `for` loop can be described in three stages¶

1.1.2 Common functions are just pre-programmed `for()` loops¶

1.1.4.1 The `local()` scope isolates your code from the global environment¶

1.1.5 Cycle through values using a `for()` loop¶

1.1.6 Iterating through a vector of elements in a `for()` loop¶

1.1.6.1 `for` loops run beneath the `group_by()`¶

1.2.0 Generate conditional branches using `if()` statements¶

1.2.1 More complex conditional branches may require the `else()` statement¶

1.2.2 `if()` statements can be nested¶

1.2.3 Use `if()` statements to generate system messages¶

1.2.4 The `if()` and `else` statement is an effective control flow statement for simple tasks¶

1.2.5 The `ifelse()` statement allows vectorized conditional assignment¶

1.2.6 Replace long/simple/cascading if statements with `switch()`¶

1.3.1 `while()` loops run conditionally¶

1.3.2 Using `next` and `break` to exit any kind of looping structure¶

1.3.3 `repeat` loops run endlessly unless specifically interrupted by `break`¶

2.0.0 Increasing our complexity by combining `for()` loops with `ggplot()`¶

3.1.0 Declare your own functions with `function()`¶

3.2.0 Retrieve data from your function using the `return()` command¶

3.5.0 The `stop()` function exits a function with a message¶

3.6.0 Use `tryCatch()` to identify errors without stopping¶

3.6.4 Implement a `tryCatch()` series to try and capture your error¶

3.6.5 Use `tryCatch()` to set values within your function¶

4.1.0 Keep all of your helper functions and subroutines in a file as a `source()`¶

4.2.0 Query your environment with `ls()` to find variables and functions¶

4.2.1 Check functions loaded into memory with `lsf.str()`¶

4.3.0 `save()` objects or your whole kernel memory!¶

4.3.1 `save.image()` saves your entire workspace¶

4.4.0 `load()` .RData files into memory¶